Citation :

Swathi B. H, A. B. Rajendra, "Intelligent Concrete Strength Classification Using Hybrid Neuro-Fuzzy Gradient Boosting and ANN Techniques," International Journal of Civil Engineering, vol. 13, no. 6, pp. 288-307, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I6P120

Abstract

The primary focus of this paper is to measure and classify the strength of the concrete with particular focus on the quality classification if 100% M-Sand is used in concrete instead of river sand with the addition of silica fume. Six different mixes of concrete were made by varying the proportion of cement with 0, 5, 10, 15, and 20% silica fume. It was found that the compressive strength of Mix-4 (with 10% silica fume) was 40.2MPa, which was 2% higher than that of conventional concrete and was 10.1% higher than that of the M-Sand mix. It was also noted that the split tensile strength and flexural strength increased by 15% and 14.9%, respectively. But all three properties went down 25% for a replacement of 20%. The quality classification of concrete was done using Hybrid Neuro Fuzzy Gradient Boosting, optimized using ASPO, and was compared with classical models. It was noted that the Hybrid Neuro Fuzzy Gradient Boosting model had a better accuracy rate than conventional models with an average accuracy of 97.2%, sensitivity ranging from 95.2% to 98.5%, Specificity ranging from 96.0% to 98.7%, and area under the receiver operating characteristic curve between 0.97 and 0.99. An Artificial Neural Network was also developed, and presented very high correlation coefficients (above 0.93), indicating a high potential application. From the observations, it was observed that the replacement of 10% silica fume with 100 % M-Sand showed high strength, which indicates high potential for its usage. It is also noticed that Hybrid Neuro Fuzzy Gradient Boosting has high potential for quality classification.

Keywords

Silica fume, M-Sand, Concrete strength classification, ANN, Quality assessment, Hybrid Neuro-Fuzzy Gradient Boosting.

References

1. Mehran Khan, Abdul Rehman, and Majid Ali, “Efficiency of Silica-fume Content in Plain and Natural Fiber Reinforced Concrete for Concrete Road,” Construction and Building Materials, vol. 244, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Hossein Sasanipour, Farhad Aslani, and Javad Taherinezhad, “Effect of Silica Fume on Durability of Self-Compacting Concrete Made with Waste Recycled Concrete Aggregates,” Construction and Building Materials, vol. 227, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Ismail B. Mustapha et al., “Comparative Analysis of Gradient-Boosting Ensembles for Estimation of Compressive Strength of Quaternary Blend Concrete,” International Journal of Concrete Structures and Materials, vol. 18, pp. 1-24, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Mahdi Al Quran, “Efficient and Effective Anomaly Detection in Autonomous Vehicles: A Combination of Gradient Boosting and ANFIS Algorithms,” International Journal of Fuzzy Systems, vol. 27, pp. 1421-1437, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Altyeb Altaher Taha, and Sharaf Jameel Malebary, “Hybrid Classification of Android Malware based on Fuzzy Clustering and the Gradient Boosting Machine,” Neural Computing and Applications, vol. 33, pp. 6721-6732, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Gebre Gelete, “Hybrid Extreme Gradient Boosting and Nonlinear Ensemble Models for Suspended Sediment Load Prediction in an Agricultural Catchment,” Water Resources Management, vol. 37, pp. 5759-5787, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Daniel Alcala-Gonzalez et al., “Compressive Strength-Based Classification of Eco-Friendly Concretes Using Machine Learning Models,” Materials, vol. 18, no. 23, pp. 1-18, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Rana Muhammad Adnan et al., “Applications of Advanced Optimized Neuro Fuzzy Models for Enhancing Daily Suspended Sediment Load Prediction,” Computer Modeling in Engineering and Sciences, vol. 143, no. 1, pp. 1249-1272, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Jingran He et al., “Stochastic Modelling of In-Structure Concrete Strength based on Stochastic Damage Model and Burr Distribution,” Structural Safety, vol. 108, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Kunpeng Cai et al., “Numerical Simulation of Concrete Strength Based on Microstructure and Mineral Composition analysis using Micro-CT and XRD Technology,” Construction and Building Materials, vol. 432, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Rohan Sawant et al., “Identification of Sustainability factors of Self-Compacting Geopolymer Concrete for precast construction using SEM,” E3S Web of Conferences, vol. 405, pp. 1-18, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Rohan Sawant, Deepa A. Joshi, and Radhika Menon, “Sustainable Paver Block Development using Recycled Plastic Waste and Fiber Reinforced Geopolymer Concrete,” Discover Applied Sciences, vol. 7, pp. 1-18, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Rohan Sawant, Deepa A. Joshi, and Radhika Menon, “Prediction and Optimization of Self-Compacting Geopolymer Concrete with and without Steel Fibres using Response Surface Methodology,” Asian Journal of Civil Engineering, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
14. R. Surya Prakash, and N. Parthasarathi, “Transient State Analysis of Rehabilitated RC Beams using Finite Element Modelling and Prediction using an Artificial Neural Network,” Engineering Research Express, vol. 6, no. 2, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. R. Sawant, D. A. Joshi, and R. Menon, “Advanced Exploration of Current State-of-the-art of Practices of Fiber-Reinforced Self-compacting Geopolymer Concrete,” Materials Science & Engineering Technology, vol. 56, no. 8, pp. 1070-1095, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Rendong Shi et al., “Predictions of Concrete Compressive Strength based on a Hybrid Algorithm of GA-BP,” Advances in Engineering Research: Proceedings of the 4^th Annual International Conference on Material Engineering and Application (ICMEA 2017), vol. 146, pp. 265-270, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Behnoush Farokhzadeh, Mohammad Ehteram, and Somayeh Soltani-Gerdefaramarzi, “A Novel Hybrid Optimization–Decomposition–Neuro-Fuzzy Approach for Pan Evaporation Prediction,” Theoretical and Applied Climatology, vol. 156, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Ali Nik-Khorasani, Ali Mehrizi, and Hadi Sadoghi-Yazdi, “Robust Hybrid Learning Approach for Adaptive Neuro-Fuzzy Inference Systems,” Fuzzy Sets and Systems, vol. 481, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Eman F. Saleh, Ahmad N. Tarawneh, and Hasan N. Katkhuda, “A Comprehensive Evaluation of Existing and New Model-Identification Approaches for Non-Destructive Concrete Strength Assessment,” Construction and Building Materials, vol. 334, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Yanhui Zhong et al., “Research on Detection Method of Concrete Compressive Strength Based on Dielectric Properties,” Journal of Building Engineering, vol. 76, pp. 1-24, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Matthew DF Mcinnes et al., “Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies: The PRISMA-DTA Statement,” Journal of the American Medical Association, vol. 319, no. 4, pp. 388-396, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Rohan Sawant, Deepa A. Joshi, and Radhika Menon, “Investigation on Key Factors Affecting Strength of Fiber Reinforced Self-Compacting Geopolymer Precast Concrete using SPSS,” E3S Web of Conferences, vol. 596, pp. 1-8, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Ashutosh Sharma et al., “Synergistic Integration of 5G-Enabled Cloud Native Infrastructures with Advanced Technologies for Urban Safety Enhancement,” IEEE Transactions on Consumer Electronics, vol. 71, no. 2, pp. 5321-5334, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Davide Chicco, and Giuseppe Jurman, “The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation,” BMC Genomics, vol. 21, pp. 1-13, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Mubbashir Ayub et al., “An Effective Model for Jaccard Coefficient to Increase the Performance of Collaborative Filtering,” Arabian Journal for Science and Engineering, vol. 45, pp. 9997-10017, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Ahmed M. Gomaa et al., “Machine Learning-Driven Insights for Concrete Compressive Strength Prediction: A bibliometric Analysis,” International Journal of Engineering and Artificial Intelligence Art Design, vol. 1, no. 1, pp. 1-22, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Haiyu Li et al., “Compressive Strength Prediction of Fly Ash-Based Concrete Using Single and Hybrid Machine Learning Models,” Buildings, vol. 14, no. 10, pp. 1-30, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Andrea Miano et al., “Reliability Estimation of the Compressive Concrete Strength Based on Non-Destructive Tests,” Sustainability, vol. 15, no. 19, pp. 1-19, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
29. R. Surya Prakash, and N. Parthasarathi, “Experimental and Numerical Study on FRP-Rehabilitated RC Beam-column Joints at High Temperature with Artificial Neural Network,” Scientific Reports, vol. 15, pp. 1-26, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
30. M. Vishnupriyan, and R. Annadurai, “A Study on the Macro-Properties of PCB Fiber-Reinforced Concrete from Recycled Electronic Waste and Validation of Results using RSM and ANN,” Asian Journal of Civil Engineering, vol. 24, pp. 1667-1680, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]